© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 2279
    Prev
    Next
    INDEX
    Explanations

    code-like entities or file attributes, sometimes involving hex codes and specific naming conventions

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مواليد
    -0.67
    pozycji
    -0.61
    WindowConstants
    -0.61
    iyle
    -0.60
    
    -0.55
     Exteriores
    -0.52
     relatifs
    -0.50
    zburg
    -0.50
     Dodson
    -0.50
     /\.
    -0.50
    POSITIVE LOGITS
     AssemblyCulture
    0.72
     Sixteenth
    0.58
    entieth
    0.53
    liothèque
    0.50
    esez
    0.49
     sixteenth
    0.49
    abetes
    0.49
    Ⅵ
    0.48
     cerve
    0.47
    ---*/
    0.46
    Activations Density 0.050%

    No Known Activations